A Multi-Criteria Model for Prioritizing Product Backlog Items in AI and Data Science Projects
Resumo
Agile AI and Data Science projects involve backlog prioritization decisions under uncertainty, metric-driven experimentation, resource constraints, and technical risks. This paper proposes a multi-criteria model to support the prioritization of Product Backlog Items during sprint planning. Each item is represented by criteria such as criticality, dependency blocking power, distance to target metrics, expected metric gain, effort efficiency, resource fit, urgency, uncertainty reduction, risk mitigation, and historical prioritization balance. The proposed model can be combined with Pareto-based prioritization, weighted aggregation, and resource-aware selection, offering a structured and adaptable mechanism to support decisionmaking in agile AI and Data Science projects.
Palavras-chave:
Agile Software Development, Product Backlog Prioritization, AI Projects, Data Science Projects, Multi-Criteria Decision Analysis, Sprint Planning, Pareto Dominance
Referências
Philip Achimugu, Ali Selamat, Roliana Ibrahim, and Mohd Naz’ri Mahrin. 2014. A Systematic Literature Review of Software Requirements Prioritization Research. Information and Software Technology 56, 6 (2014), 568–585. DOI: 10.1016/j.infsof.2014.02.001
Saleema Amershi, Andrew Begel, Christian Bird, Robert DeLine, Harald Gall, Ece Kamar, Nachiappan Nagappan, Besmira Nushi, and Thomas Zimmermann. 2019. Software Engineering for Machine Learning: A Case Study. In Proceedings of the 41st International Conference on Software Engineering: Software Engineering in Practice. IEEE Press, 291–300. DOI: 10.1109/ICSE-SEIP.2019.00042
Dominik Kreuzberger, Niklas Kühl, and Sebastian Hirschl. 2023. Machine Learning Operations (MLOps): Overview, Definition, and Architecture. IEEE Access 11 (2023), 31866–31879. DOI: 10.1109/ACCESS.2023.3262138
Nithya Sambasivan, Shivani Kapania, Hannah Highfill, Diana Akrong, Praveen Paritosh, and Lora M. Aroyo. 2021. “Everyone Wants to Do the Model Work, Not the Data Work”: Data Cascades in High-Stakes AI. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Article 39, 15 pages. DOI: 10.1145/3411764.3445518
David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-François Crespo, and Dan Dennison. 2015. Hidden Technical Debt in Machine Learning Systems. In Advances in Neural Information Processing Systems, Vol. 28. 2503–2511.
Alex Serban, Koen van der Blom, Holger H. Hoos, and Joost Visser. 2024. Software Engineering Practices for Machine Learning: Adoption, Effects, and Team Assessment. Information and Software Technology 169 (2024), 107421. DOI: 10.1016/j.infsof.2023.107421
Zhiyuan Wan, Xin Xia, David Lo, and Gail C. Murphy. 2021. How Does Machine Learning Change Software Development Practices? IEEE Transactions on Software Engineering 47, 9 (2021), 1857–1871. DOI: 10.1109/TSE.2019.2937083
Saleema Amershi, Andrew Begel, Christian Bird, Robert DeLine, Harald Gall, Ece Kamar, Nachiappan Nagappan, Besmira Nushi, and Thomas Zimmermann. 2019. Software Engineering for Machine Learning: A Case Study. In Proceedings of the 41st International Conference on Software Engineering: Software Engineering in Practice. IEEE Press, 291–300. DOI: 10.1109/ICSE-SEIP.2019.00042
Dominik Kreuzberger, Niklas Kühl, and Sebastian Hirschl. 2023. Machine Learning Operations (MLOps): Overview, Definition, and Architecture. IEEE Access 11 (2023), 31866–31879. DOI: 10.1109/ACCESS.2023.3262138
Nithya Sambasivan, Shivani Kapania, Hannah Highfill, Diana Akrong, Praveen Paritosh, and Lora M. Aroyo. 2021. “Everyone Wants to Do the Model Work, Not the Data Work”: Data Cascades in High-Stakes AI. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Article 39, 15 pages. DOI: 10.1145/3411764.3445518
David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-François Crespo, and Dan Dennison. 2015. Hidden Technical Debt in Machine Learning Systems. In Advances in Neural Information Processing Systems, Vol. 28. 2503–2511.
Alex Serban, Koen van der Blom, Holger H. Hoos, and Joost Visser. 2024. Software Engineering Practices for Machine Learning: Adoption, Effects, and Team Assessment. Information and Software Technology 169 (2024), 107421. DOI: 10.1016/j.infsof.2023.107421
Zhiyuan Wan, Xin Xia, David Lo, and Gail C. Murphy. 2021. How Does Machine Learning Change Software Development Practices? IEEE Transactions on Software Engineering 47, 9 (2021), 1857–1871. DOI: 10.1109/TSE.2019.2937083
Publicado
11/09/2026
Como Citar
NASCIMENTO, Dimas Cassimiro; SILVA, Daliton da; VANDERLEI, Igor Medeiros; PINHEIRO, Rian Gabriel Santos; ANDRADE, Rodrigo Cardoso.
A Multi-Criteria Model for Prioritizing Product Backlog Items in AI and Data Science Projects. In: WORKSHOP BRASILEIRO DE ENGENHARIA DE SOFTWARE INTELIGENTE (ISE), 5. , 2026, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 117-120.
DOI: https://doi.org/10.5753/ise.2026.32545.
